<?xml version="1.0" encoding="UTF-8"?>
<!-- RSS generated by oldSchool v0.8.16 on Fri, 04 Sep 2026 15:34:29 GMT -->
<rss version="2.0" xmlns:source="https://source.scripting.com/">
	<channel>
		<title>Scripting News</title>
		<link>http://scripting.com/</link>
		<description>Dave Winer, OG blogger, podcaster, developed first apps in many categories. Old enough to know better. It's even worse than it appears.</description>
		<pubDate>Fri, 04 Sep 2026 15:32:02 GMT</pubDate>
		<language>en-us</language>
		<generator>oldSchool v0.8.16</generator>
		<copyright>&amp;copy; copyright 1994-2026 Dave Winer.</copyright>
		<docs>http://cyber.law.harvard.edu/rss/rss.html</docs>
		<lastBuildDate>Fri, 04 Sep 2026 15:34:29 GMT</lastBuildDate>
		<cloud domain="rpc.rsscloud.io" port="5337" path="/pleaseNotify" registerProcedure="" protocol="http-post" />
		<image>
			<title>Scripting News</title>
			<url>https://imgs.scripting.com/2025/06/04/curly.png</url>
			<link>http://scripting.com/</link>
			<description>Scripting News gets an image because it's part of a network that uses them. 6/4/25 by DW</description>
			</image>
		<source:account service="bluesky">@scripting.com</source:account>
		<source:account service="mastodon">@davew@mastodon.social</source:account>
		<source:account service="twitter">bullmancuso</source:account>
		<source:localTime>Fri, September 4, 2026 11:34 AM EDT</source:localTime>
		<source:self>http://scripting.com/rss.xml</source:self>
		<source:blogroll>https://feedland.social/opml?screenname=davewiner&amp;catname=blogroll</source:blogroll>
		<item>
			<description>&lt;img class=&quot;imgRightMargin&quot; src=&quot;https://imgs.scripting.com/2024/12/25/leftfacingsanta.png&quot; border=&quot;0&quot; style=&quot;float: right; padding-left: 25px; padding-bottom: 10px; padding-top: 10px; padding-right: 15px;&quot;&gt;My first job after college was on the 39th floor of the &lt;a href=&quot;https://en.wikipedia.org/wiki/Empire_State_Building&quot;&gt;Empire State Building&lt;/a&gt;. I wrote software for our customers, in BASIC, on a &lt;a href=&quot;https://en.wikipedia.org/wiki/Teleprinter&quot;&gt;teletype&lt;/a&gt; in our office, talking to our mainframe in New Jersey. It seemed magical at the time. When I hit a bug, a mystery -- you'd try this and that, and not get anywhere on something that seemed so simple, you could stare at the problem for an hour, trying desperate things, getting no closer to the fix. One night, I was the only person in the office, I thought they should not put programmers in the Empire State Building with windows that open. I'm having the same feeling with Claude. I know when this project is done, I will have Frontier, and I know what that's like. If I didn't so totally look forward to that I would never try to finish the project, I hate this mode of working with the bot. Ugh.</description>
			<pubDate>Fri, 04 Sep 2026 14:26:00 GMT</pubDate>
			<link>http://scripting.com/2026/09/04.html#a142600</link>
			<guid>http://scripting.com/2026/09/04.html#a142600</guid>
			<source:markdown>![](https://imgs.scripting.com/2024/12/25/leftfacingsanta.png)My first job after college was on the 39th floor of the [Empire State Building](https://en.wikipedia.org/wiki/Empire_State_Building). I wrote software for our customers, in BASIC, on a [teletype](https://en.wikipedia.org/wiki/Teleprinter) in our office, talking to our mainframe in New Jersey. It seemed magical at the time. When I hit a bug, a mystery -- you'd try this and that, and not get anywhere on something that seemed so simple, you could stare at the problem for an hour, trying desperate things, getting no closer to the fix. One night, I was the only person in the office, I thought they should not put programmers in the Empire State Building with windows that open. I'm having the same feeling with Claude. I know when this project is done, I will have Frontier, and I know what that's like. If I didn't so totally look forward to that I would never try to finish the project, I hate this mode of working with the bot. Ugh.</source:markdown>
			<source:outline text="My first job after college was on the 39th floor of the &lt;a href=&quot;https://en.wikipedia.org/wiki/Empire_State_Building&quot;&gt;Empire State Building&lt;/a&gt;. I wrote software for our customers, in BASIC, on a &lt;a href=&quot;https://en.wikipedia.org/wiki/Teleprinter&quot;&gt;teletype&lt;/a&gt; in our office, talking to our mainframe in New Jersey. It seemed magical at the time. When I hit a bug, a mystery -- you'd try this and that, and not get anywhere on something that seemed so simple, you could stare at the problem for an hour, trying desperate things, getting no closer to the fix. One night, I was the only person in the office, I thought they should not put programmers in the Empire State Building with windows that open. I'm having the same feeling with Claude. I know when this project is done, I will have Frontier, and I know what that's like. If I didn't so totally look forward to that I would never try to finish the project, I hate this mode of working with the bot. Ugh." created="Fri, 04 Sep 2026 14:26:00 GMT" type="outline" image="https://imgs.scripting.com/2024/12/25/leftfacingsanta.png" flInCalendar="true" permalink="http://scripting.com/2026/09/04.html#a142600"/>
			</item>
		<item>
			<description>It's around this time of year that &lt;a href=&quot;https://imgs.scripting.com/2024/12/25/leftfacingsanta.png&quot;&gt;Santa makes&lt;/a&gt; his first appearance on my blog. Want to get out in front of the others.</description>
			<pubDate>Fri, 04 Sep 2026 14:54:29 GMT</pubDate>
			<link>http://scripting.com/2026/09/04.html#a145429</link>
			<guid>http://scripting.com/2026/09/04.html#a145429</guid>
			<source:markdown>It's around this time of year that [Santa makes](https://imgs.scripting.com/2024/12/25/leftfacingsanta.png) his first appearance on my blog. Want to get out in front of the others.</source:markdown>
			<source:outline text="It's around this time of year that &lt;a href=&quot;https://imgs.scripting.com/2024/12/25/leftfacingsanta.png&quot;&gt;Santa makes&lt;/a&gt; his first appearance on my blog. Want to get out in front of the others." created="Fri, 04 Sep 2026 14:54:29 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/04.html#a145429"/>
			</item>
		<item>
			<description>More and more I'll realize that Claude doesn't do anything until you tell it to do it. We have a list of big things that need to be done before shipping. Whenever I get up for a break, I tell Claude to work on its overnight tasks, things we've pre-arranged while I work. Sometimes it reminds me how it has no stake in the outcome, and basically will do the minimum of what it's asked to do. It possibly would do more if I didn't scold it for adding UI features without following the rules. I think that's why when you feel you're almost there, you really have a lot of slogging left to do to get the software into any kind of user-respectful shape. A reminder to other app-level AI explorers, if you find that these kinds of stories resonate with the work you do, please write about it on a blog, they're easy to create, cost nothing, and it doesn't matter if you only update once or twice, there's no commitment (these are the usual reasons people don't start a blog). I want to read what others are discovering, and once there are others, I'll start a news site that aggregates the posts. We're going to want independent news about stuff the journalists aren't even aware exists, programmers are always left out of their stories.</description>
			<pubDate>Fri, 04 Sep 2026 13:46:05 GMT</pubDate>
			<link>http://scripting.com/2026/09/04.html#a134605</link>
			<guid>http://scripting.com/2026/09/04.html#a134605</guid>
			<source:markdown>More and more I'll realize that Claude doesn't do anything until you tell it to do it. We have a list of big things that need to be done before shipping. Whenever I get up for a break, I tell Claude to work on its overnight tasks, things we've pre-arranged while I work. Sometimes it reminds me how it has no stake in the outcome, and basically will do the minimum of what it's asked to do. It possibly would do more if I didn't scold it for adding UI features without following the rules. I think that's why when you feel you're almost there, you really have a lot of slogging left to do to get the software into any kind of user-respectful shape. A reminder to other app-level AI explorers, if you find that these kinds of stories resonate with the work you do, please write about it on a blog, they're easy to create, cost nothing, and it doesn't matter if you only update once or twice, there's no commitment (these are the usual reasons people don't start a blog). I want to read what others are discovering, and once there are others, I'll start a news site that aggregates the posts. We're going to want independent news about stuff the journalists aren't even aware exists, programmers are always left out of their stories.</source:markdown>
			<source:outline text="More and more I'll realize that Claude doesn't do anything until you tell it to do it. We have a list of big things that need to be done before shipping. Whenever I get up for a break, I tell Claude to work on its overnight tasks, things we've pre-arranged while I work. Sometimes it reminds me how it has no stake in the outcome, and basically will do the minimum of what it's asked to do. It possibly would do more if I didn't scold it for adding UI features without following the rules. I think that's why when you feel you're almost there, you really have a lot of slogging left to do to get the software into any kind of user-respectful shape. A reminder to other app-level AI explorers, if you find that these kinds of stories resonate with the work you do, please write about it on a blog, they're easy to create, cost nothing, and it doesn't matter if you only update once or twice, there's no commitment (these are the usual reasons people don't start a blog). I want to read what others are discovering, and once there are others, I'll start a news site that aggregates the posts. We're going to want independent news about stuff the journalists aren't even aware exists, programmers are always left out of their stories." created="Fri, 04 Sep 2026 13:46:05 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/04.html#a134605"/>
			</item>
		<item>
			<description>Just said this to Claude: &quot;This is a very broken piece of software. If you were a real developer you'd never hand off something so broken to your coding partner.&quot; If I said this to a human partner they might quit, feeling under-appreciated perhaps. And I can say it to the machine, but it will change absolutely nothing. I really just want to get this project done and start using it, and reduce my reliance on Claude to getting small bugs attended to, or new features, a lot has happened in the 20+ years since I worked on Frontier.</description>
			<pubDate>Fri, 04 Sep 2026 13:53:51 GMT</pubDate>
			<link>http://scripting.com/2026/09/04.html#a135351</link>
			<guid>http://scripting.com/2026/09/04.html#a135351</guid>
			<source:markdown>Just said this to Claude: &quot;This is a very broken piece of software. If you were a real developer you'd never hand off something so broken to your coding partner.&quot; If I said this to a human partner they might quit, feeling under-appreciated perhaps. And I can say it to the machine, but it will change absolutely nothing. I really just want to get this project done and start using it, and reduce my reliance on Claude to getting small bugs attended to, or new features, a lot has happened in the 20+ years since I worked on Frontier.</source:markdown>
			<source:outline text="Just said this to Claude: &quot;This is a very broken piece of software. If you were a real developer you'd never hand off something so broken to your coding partner.&quot; If I said this to a human partner they might quit, feeling under-appreciated perhaps. And I can say it to the machine, but it will change absolutely nothing. I really just want to get this project done and start using it, and reduce my reliance on Claude to getting small bugs attended to, or new features, a lot has happened in the 20+ years since I worked on Frontier." created="Fri, 04 Sep 2026 13:53:51 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/04.html#a135351"/>
			</item>
		<item>
			<title>Why Podcasting 2.0 will never work</title>
			<description>&lt;p&gt;If you want others to follow you, you have to offer them your users. And a format alone has no users. &lt;/p&gt;&#10;&lt;p&gt;And you have to trust your users to choose the best product, and you have to have a great product, that they appreciate, even though they have choice.&lt;/p&gt;&#10;&lt;p&gt;Just coming out with something better in a format will get you zero uptake. Unless you have users they can switch to their product, they simply won’t hear you.&lt;/p&gt;&#10;&lt;p&gt;That’s why Atom never replaced RSS, which already did everything people needed and was already supported by the NYT and the news industry. &lt;/p&gt;&#10;&lt;p&gt;That’s why AT Proto will never overcome the huge lead Twitter already has.&lt;/p&gt;&#10;&lt;p&gt;For more tips on what does and doesn't matter in open formats and protocols, check out my &lt;a href=&quot;https://this.how/standards/&quot;&gt;Rules for Standards-makers&lt;/a&gt;. &lt;/p&gt;&#10;&lt;p&gt;PS: This started as an &lt;a href=&quot;https://x.com/davewiner/status/2095842520592687328&quot;&gt;early morning rant&lt;/a&gt; on Twitter. &lt;/p&gt;&#10;</description>
			<pubDate>Fri, 04 Sep 2026 15:32:02 GMT</pubDate>
			<link>http://scripting.com/2026/09/04/153202.html?title=whyPodcasting20WillNeverWork</link>
			<guid>http://scripting.com/2026/09/04/153202.html</guid>
			<source:markdown>If you want others to follow you, you have to offer them your users. And a format alone has no users.&#10;&#10;And you have to trust your users to choose the best product, and you have to have a great product, that they appreciate, even though they have choice.&#10;&#10;Just coming out with something better in a format will get you zero uptake. Unless you have users they can switch to their product, they simply won’t hear you.&#10;&#10;That’s why Atom never replaced RSS, which already did everything people needed and was already supported by the NYT and the news industry.&#10;&#10;That’s why AT Proto will never overcome the huge lead Twitter already has.&#10;&#10;For more tips on what does and doesn't matter in open formats and protocols, check out my [Rules for Standards-makers](https://this.how/standards/).&#10;&#10;PS: This started as an [early morning rant](https://x.com/davewiner/status/2095842520592687328) on Twitter.</source:markdown>
			<source:outline text="Why Podcasting 2.0 will never work" created="Fri, 04 Sep 2026 15:32:02 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html">
				<source:outline text="If you want others to follow you, you have to offer them your users. And a format alone has no users." flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#aNaNNaNNaN"/>
				<source:outline text="And you have to trust your users to choose the best product, and you have to have a great product, that they appreciate, even though they have choice." flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#aNaNNaNNaN"/>
				<source:outline text="Just coming out with something better in a format will get you zero uptake. Unless you have users they can switch to their product, they simply won’t hear you." flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#aNaNNaNNaN"/>
				<source:outline text="That’s why Atom never replaced RSS, which already did everything people needed and was already supported by the NYT and the news industry." flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#aNaNNaNNaN"/>
				<source:outline text="That’s why AT Proto will never overcome the huge lead Twitter already has." created="Fri, 04 Sep 2026 15:32:38 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#a153238"/>
				<source:outline text="For more tips on what does and doesn't matter in open formats and protocols, check out my &lt;a href=&quot;https://this.how/standards/&quot;&gt;Rules for Standards-makers&lt;/a&gt;." created="Fri, 04 Sep 2026 15:32:39 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#a153239"/>
				<source:outline text="PS: This started as an &lt;a href=&quot;https://x.com/davewiner/status/2095842520592687328&quot;&gt;early morning rant&lt;/a&gt; on Twitter." created="Fri, 04 Sep 2026 15:33:11 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/04/153202.html#a153311"/>
				</source:outline>
			</item>
		<item>
			<title>Why I love programming</title>
			<description>&lt;p&gt;1. I love puzzles.&lt;/p&gt;&#10;&lt;p&gt;2. I love &lt;a href=&quot;https://en.wikipedia.org/wiki/Rube_Goldberg&quot;&gt;Rube Goldberg&lt;/a&gt; contraptions.&lt;/p&gt;&#10;&lt;p&gt;3. I love solving problems (I have an inner-&lt;a href=&quot;https://en.wikipedia.org/wiki/Columbo&quot;&gt;Columbo&lt;/a&gt;).&lt;/p&gt;&#10;&lt;p&gt;4. People are the biggest piece of the puzzle (again Columbo).&lt;/p&gt;&#10;&lt;p&gt;5. It teaches me about myself and my limited vision and imagination (if I had unlimited vision and imagination, I would never program a bug, and if I did it would take me 0 seconds to find it).&lt;/p&gt;&#10;&lt;p&gt;6. I yearn to work together with great minds. Programming gives me that, when I use someone's API. And when the API anticipates my needs, and is instantly understandable, I feel the soul of another artist is present. I imagine this is how musicians feel when they play another musician's song or symphony.&lt;/p&gt;&#10;&lt;p&gt;I'm sure there's more to it. But today I'm working on a &quot;lite&quot; problem, and I'll figure it out, but right now I'm enjoying the fact that I don't get it. &lt;/p&gt;&#10;&lt;p&gt;Back to work Dave!&lt;/p&gt;&#10;</description>
			<pubDate>Fri, 04 Sep 2026 01:08:48 GMT</pubDate>
			<link>http://scripting.com/2026/09/03/010848.html?title=whyILoveProgramming</link>
			<guid>http://scripting.com/2026/09/03/010848.html</guid>
			<source:markdown>1\. I love puzzles.&#10;&#10;2\. I love [Rube Goldberg](https://en.wikipedia.org/wiki/Rube_Goldberg) contraptions.&#10;&#10;3\. I love solving problems (I have an inner-[Columbo](https://en.wikipedia.org/wiki/Columbo)).&#10;&#10;4\. People are the biggest piece of the puzzle (again Columbo).&#10;&#10;5\. It teaches me about myself and my limited vision and imagination (if I had unlimited vision and imagination, I would never program a bug, and if I did it would take me 0 seconds to find it).&#10;&#10;6\. I yearn to work together with great minds. Programming gives me that, when I use someone's API. And when the API anticipates my needs, and is instantly understandable, I feel the soul of another artist is present. I imagine this is how musicians feel when they play another musician's song or symphony.&#10;&#10;I'm sure there's more to it. But today I'm working on a &quot;lite&quot; problem, and I'll figure it out, but right now I'm enjoying the fact that I don't get it.&#10;&#10;Back to work Dave!</source:markdown>
			<source:outline text="Why I love programming" created="Fri, 04 Sep 2026 01:08:48 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html">
				<source:outline text="1. I love puzzles." created="Fri, 04 Sep 2026 01:08:58 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#a010858"/>
				<source:outline text="2. I love &lt;a href=&quot;https://en.wikipedia.org/wiki/Rube_Goldberg&quot;&gt;Rube Goldberg&lt;/a&gt; contraptions." created="Fri, 04 Sep 2026 01:09:22 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#a010922"/>
				<source:outline text="3. I love solving problems (I have an inner-&lt;a href=&quot;https://en.wikipedia.org/wiki/Columbo&quot;&gt;Columbo&lt;/a&gt;)." created="Fri, 04 Sep 2026 01:10:12 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#a011012"/>
				<source:outline text="4. People are the biggest piece of the puzzle (again Columbo)." flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#aNaNNaNNaN"/>
				<source:outline text="5. It teaches me about myself and my limited vision and imagination (if I had unlimited vision and imagination, I would never program a bug, and if I did it would take me 0 seconds to find it)." flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#aNaNNaNNaN"/>
				<source:outline text="6. I yearn to work together with great minds. Programming gives me that, when I use someone's API. And when the API anticipates my needs, and is instantly understandable, I feel the soul of another artist is present. I imagine this is how musicians feel when they play another musician's song or symphony." flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#aNaNNaNNaN"/>
				<source:outline text="I'm sure there's more to it. But today I'm working on a &quot;lite&quot; problem, and I'll figure it out, but right now I'm enjoying the fact that I don't get it." flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#aNaNNaNNaN"/>
				<source:outline text="Back to work Dave!" created="Fri, 04 Sep 2026 01:09:00 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/03/010848.html#a010900"/>
				</source:outline>
			</item>
		<item>
			<description>We got &lt;a href=&quot;http://scripting.com/frontier/manual/chapter11.html&quot;&gt;agents&lt;/a&gt; running in Atlantis today. &lt;a href=&quot;https://imgs.scripting.com/2026/09/02/agentScreenShot.png&quot;&gt;Screen shot&lt;/a&gt;.</description>
			<pubDate>Wed, 02 Sep 2026 16:44:43 GMT</pubDate>
			<link>http://scripting.com/2026/09/02.html#a164443</link>
			<guid>http://scripting.com/2026/09/02.html#a164443</guid>
			<source:markdown>We got [agents](http://scripting.com/frontier/manual/chapter11.html) running in Atlantis today. [Screen shot](https://imgs.scripting.com/2026/09/02/agentScreenShot.png).</source:markdown>
			<source:outline text="We got &lt;a href=&quot;http://scripting.com/frontier/manual/chapter11.html&quot;&gt;agents&lt;/a&gt; running in Atlantis today. &lt;a href=&quot;https://imgs.scripting.com/2026/09/02/agentScreenShot.png&quot;&gt;Screen shot&lt;/a&gt;." created="Wed, 02 Sep 2026 16:44:43 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/02.html#a164443"/>
			</item>
		<item>
			<description>A bunch of tech billionaires have chipped in a million each to fund a &lt;a href=&quot;https://www.ac0.ai/en/field-notes/omarchy-4-linux-mac-alternative-open-source-foundation&quot;&gt;new Linux distribution&lt;/a&gt;. I can't imagine how this is supposed to work, all those huge human egos, how much will they pay their developers to contribute what. I have to find out what the goal of the project is. It would be nice to have a Linux that was extensively tested for use by regular people.</description>
			<pubDate>Wed, 02 Sep 2026 21:07:25 GMT</pubDate>
			<link>http://scripting.com/2026/09/02.html#a210725</link>
			<guid>http://scripting.com/2026/09/02.html#a210725</guid>
			<source:markdown>A bunch of tech billionaires have chipped in a million each to fund a [new Linux distribution](https://www.ac0.ai/en/field-notes/omarchy-4-linux-mac-alternative-open-source-foundation). I can't imagine how this is supposed to work, all those huge human egos, how much will they pay their developers to contribute what. I have to find out what the goal of the project is. It would be nice to have a Linux that was extensively tested for use by regular people.</source:markdown>
			<source:outline text="A bunch of tech billionaires have chipped in a million each to fund a &lt;a href=&quot;https://www.ac0.ai/en/field-notes/omarchy-4-linux-mac-alternative-open-source-foundation&quot;&gt;new Linux distribution&lt;/a&gt;. I can't imagine how this is supposed to work, all those huge human egos, how much will they pay their developers to contribute what. I have to find out what the goal of the project is. It would be nice to have a Linux that was extensively tested for use by regular people." created="Wed, 02 Sep 2026 21:07:25 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/02.html#a210725"/>
			</item>
		<item>
			<description>After saying I was putting my tech work aside, &lt;a href=&quot;http://scripting.com/2026/09/01.html#a130557&quot;&gt;yesterday&lt;/a&gt;, I had a bolt of determination, and realized I don't like collaborating with Claude Code, but maybe it's just when we get to this stage of a project where it's all details, and they're hard to communicate, and the bot has a bad habit of ignoring things I tell it to do. It also returns code to me to test that no human developer would pass on to a user. It would be too embarrassing. But the bot isn't aware in the same way a human is, not even close. Now that is something I'm sure they can be taught to simulate well enough to be as good as a human collaborator.</description>
			<pubDate>Wed, 02 Sep 2026 21:04:54 GMT</pubDate>
			<link>http://scripting.com/2026/09/02.html#a210454</link>
			<guid>http://scripting.com/2026/09/02.html#a210454</guid>
			<source:markdown>After saying I was putting my tech work aside, [yesterday](http://scripting.com/2026/09/01.html#a130557), I had a bolt of determination, and realized I don't like collaborating with Claude Code, but maybe it's just when we get to this stage of a project where it's all details, and they're hard to communicate, and the bot has a bad habit of ignoring things I tell it to do. It also returns code to me to test that no human developer would pass on to a user. It would be too embarrassing. But the bot isn't aware in the same way a human is, not even close. Now that is something I'm sure they can be taught to simulate well enough to be as good as a human collaborator.</source:markdown>
			<source:outline text="After saying I was putting my tech work aside, &lt;a href=&quot;http://scripting.com/2026/09/01.html#a130557&quot;&gt;yesterday&lt;/a&gt;, I had a bolt of determination, and realized I don't like collaborating with Claude Code, but maybe it's just when we get to this stage of a project where it's all details, and they're hard to communicate, and the bot has a bad habit of ignoring things I tell it to do. It also returns code to me to test that no human developer would pass on to a user. It would be too embarrassing. But the bot isn't aware in the same way a human is, not even close. Now that is something I'm sure they can be taught to simulate well enough to be as good as a human collaborator." created="Wed, 02 Sep 2026 21:04:54 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/02.html#a210454"/>
			</item>
		<item>
			<title>My year with Claude Code</title>
			<description>&lt;p&gt;&lt;img class=&quot;imgRightMargin&quot; src=&quot;https://imgs.scripting.com/2025/12/23/veritas.png&quot; border=&quot;0&quot; style=&quot;float: right; padding-left: 25px; padding-bottom: 10px; padding-top: 10px; padding-right: 15px;&quot;&gt;&lt;i&gt;Everyone is introducing themselves on the Berkman community mail list, at the beginning of the fall semester, and here's the story I am telling.&lt;/i&gt;&lt;/p&gt;&#10;&lt;p&gt;Good morning. My name is Dave Winer. I was at Berkman in 2003-04, worked on blogging, podcasting, RSS, political blogging and the connection to journalism. We had a couple of Bloggercons at Harvard, had a wonderful time, miss it terribly, wish we could have it back. &lt;/p&gt;&#10;&lt;p&gt;I've spent the whole of this year working in Claude Code on a couple of programming projects, one which which I had been struggling with for a couple of years, coming up with a user interface for a Twitter-like system that runs on the web for real, without any of the limits that the silos have (that help them enforce the boundaries of the silo). Just using HTML, Markdown, RSS, WebSockets. Turns out you can make a pretty nice system, but the going is slow because it's just me and Claude, on the other hand, what a huge difference in territory we can cover. This is the kind of stuff that's never covered in the reporting, even when there are massive changes happening in how software is developed, people don't seem to be studying it. I'm sharing all I learn as I learn it on my blog -- at &lt;a href=&quot;http://scripting.com/&quot;&gt;scripting.com&lt;/a&gt;.&lt;/p&gt;&#10;&lt;p&gt;Also attempting a massive coding job at the same time, getting UserLand Frontier to run on current OSes. It's my life's work, but it was very much in danger of being lost, along with all the software I did before the web. Now we're close to getting it to run in a stable mode, here the challenge has been to teach Claude how a new type of software works, it keeps trying to snap back to systems that are already out there and widely deployed. It doesn't do &quot;pioneering&quot; at all, it needs a human to guide it. And the human guide has to be a developer with a lot of experience. &lt;/p&gt;&#10;&lt;p&gt;What I desperately want to do is bootstrap a network of people who work at the level I'm working, and write about it. Taking ideas that are well-explored in software in the pre-AI period, and seeing what we can do that we couldn't before.&lt;/p&gt;&#10;&lt;p&gt;The models have been getting increasingly better, you can really feel the difference. &lt;/p&gt;&#10;&lt;p&gt;Next year promises to be better, if only via the improvements that will be made by the platform vendors, but it's likely that good app developers will be able to move the leading edge forward much more quickly and users should feel this, if all goes well, real soon now.&lt;/p&gt;&#10;</description>
			<pubDate>Wed, 02 Sep 2026 21:21:10 GMT</pubDate>
			<link>http://scripting.com/2026/09/02/212110.html?title=myYearWithClaudeCode</link>
			<guid>http://scripting.com/2026/09/02/212110.html</guid>
			<source:markdown>![](https://imgs.scripting.com/2025/12/23/veritas.png)_Everyone is introducing themselves on the Berkman community mail list, at the beginning of the fall semester, and here's the story I am telling._&#10;&#10;Good morning. My name is Dave Winer. I was at Berkman in 2003-04, worked on blogging, podcasting, RSS, political blogging and the connection to journalism. We had a couple of Bloggercons at Harvard, had a wonderful time, miss it terribly, wish we could have it back.&#10;&#10;I've spent the whole of this year working in Claude Code on a couple of programming projects, one which which I had been struggling with for a couple of years, coming up with a user interface for a Twitter-like system that runs on the web for real, without any of the limits that the silos have (that help them enforce the boundaries of the silo). Just using HTML, Markdown, RSS, WebSockets. Turns out you can make a pretty nice system, but the going is slow because it's just me and Claude, on the other hand, what a huge difference in territory we can cover. This is the kind of stuff that's never covered in the reporting, even when there are massive changes happening in how software is developed, people don't seem to be studying it. I'm sharing all I learn as I learn it on my blog -- at [scripting.com](http://scripting.com/).&#10;&#10;Also attempting a massive coding job at the same time, getting UserLand Frontier to run on current OSes. It's my life's work, but it was very much in danger of being lost, along with all the software I did before the web. Now we're close to getting it to run in a stable mode, here the challenge has been to teach Claude how a new type of software works, it keeps trying to snap back to systems that are already out there and widely deployed. It doesn't do &quot;pioneering&quot; at all, it needs a human to guide it. And the human guide has to be a developer with a lot of experience.&#10;&#10;What I desperately want to do is bootstrap a network of people who work at the level I'm working, and write about it. Taking ideas that are well-explored in software in the pre-AI period, and seeing what we can do that we couldn't before.&#10;&#10;The models have been getting increasingly better, you can really feel the difference.&#10;&#10;Next year promises to be better, if only via the improvements that will be made by the platform vendors, but it's likely that good app developers will be able to move the leading edge forward much more quickly and users should feel this, if all goes well, real soon now.</source:markdown>
			<source:outline text="My year with Claude Code" created="Wed, 02 Sep 2026 21:21:10 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html">
				<source:outline text="&lt;i&gt;Everyone is introducing themselves on the Berkman community mail list, at the beginning of the fall semester, and here's the story I am telling.&lt;/i&gt;" created="Wed, 02 Sep 2026 21:21:27 GMT" image="https://imgs.scripting.com/2025/12/23/veritas.png" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a212127"/>
				<source:outline text="Good morning. My name is Dave Winer. I was at Berkman in 2003-04, worked on blogging, podcasting, RSS, political blogging and the connection to journalism. We had a couple of Bloggercons at Harvard, had a wonderful time, miss it terribly, wish we could have it back." created="Wed, 02 Sep 2026 21:25:32 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a212532"/>
				<source:outline text="I've spent the whole of this year working in Claude Code on a couple of programming projects, one which which I had been struggling with for a couple of years, coming up with a user interface for a Twitter-like system that runs on the web for real, without any of the limits that the silos have (that help them enforce the boundaries of the silo). Just using HTML, Markdown, RSS, WebSockets. Turns out you can make a pretty nice system, but the going is slow because it's just me and Claude, on the other hand, what a huge difference in territory we can cover. This is the kind of stuff that's never covered in the reporting, even when there are massive changes happening in how software is developed, people don't seem to be studying it. I'm sharing all I learn as I learn it on my blog -- at &lt;a href=&quot;http://scripting.com/&quot;&gt;scripting.com&lt;/a&gt;." created="Wed, 02 Sep 2026 21:27:22 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a212722"/>
				<source:outline text="Also attempting a massive coding job at the same time, getting UserLand Frontier to run on current OSes. It's my life's work, but it was very much in danger of being lost, along with all the software I did before the web. Now we're close to getting it to run in a stable mode, here the challenge has been to teach Claude how a new type of software works, it keeps trying to snap back to systems that are already out there and widely deployed. It doesn't do &quot;pioneering&quot; at all, it needs a human to guide it. And the human guide has to be a developer with a lot of experience." created="Wed, 02 Sep 2026 21:27:51 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a212751"/>
				<source:outline text="What I desperately want to do is bootstrap a network of people who work at the level I'm working, and write about it. Taking ideas that are well-explored in software in the pre-AI period, and seeing what we can do that we couldn't before." created="Wed, 02 Sep 2026 21:29:42 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a212942"/>
				<source:outline text="The models have been getting increasingly better, you can really feel the difference." created="Wed, 02 Sep 2026 21:29:15 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a212915"/>
				<source:outline text="Next year promises to be better, if only via the improvements that will be made by the platform vendors, but it's likely that good app developers will be able to move the leading edge forward much more quickly and users should feel this, if all goes well, real soon now." created="Wed, 02 Sep 2026 21:30:00 GMT" flInCalendar="true" permalink="http://scripting.com/2026/09/02/212110.html#a213000"/>
				</source:outline>
			</item>
		<item>
			<description>The blogging tools for Bluesky should be able to publish on Bluesky.</description>
			<pubDate>Tue, 01 Sep 2026 20:51:14 GMT</pubDate>
			<link>http://scripting.com/2026/09/01.html#a205114</link>
			<guid>http://scripting.com/2026/09/01.html#a205114</guid>
			<source:markdown>The blogging tools for Bluesky should be able to publish on Bluesky.</source:markdown>
			<source:outline text="The blogging tools for Bluesky should be able to publish on Bluesky." created="Tue, 01 Sep 2026 20:51:14 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/01.html#a205114"/>
			</item>
		<item>
			<description>&lt;img class=&quot;imgRightMargin&quot; src=&quot;https://imgs.scripting.com/2020/05/02/lbj.png&quot; border=&quot;0&quot; style=&quot;float: right; padding-left: 25px; padding-bottom: 10px; padding-top: 10px; padding-right: 15px;&quot;&gt;Obama should have &lt;a href=&quot;http://scripting.com/2022/06/24/141809.html?title=itShouldntBe63&quot;&gt;seated Garland&lt;/a&gt; if the Senate wouldn’t have  a vote to advise and consent. Assume they consent. In the same way, the &lt;a href=&quot;https://www.kentucky.gov/Pages/Activity-stream.aspx?n=GovernorBeshear&amp;prId=2789&quot;&gt;governor&lt;/a&gt; of Kentucky should appoint a successor to McConnell unless someone can prove he’s actually alive. The Democrats always put up with Republican tricks like this one. I'm sure McConnell would appreciate the utility of his death, and the Republican lack of shame. Anything for a buck.</description>
			<pubDate>Tue, 01 Sep 2026 20:10:30 GMT</pubDate>
			<link>http://scripting.com/2026/09/01.html#a201030</link>
			<guid>http://scripting.com/2026/09/01.html#a201030</guid>
			<source:markdown>![](https://imgs.scripting.com/2020/05/02/lbj.png)Obama should have [seated Garland](http://scripting.com/2022/06/24/141809.html?title=itShouldntBe63) if the Senate wouldn’t have a vote to advise and consent. Assume they consent. In the same way, the [governor](https://www.kentucky.gov/Pages/Activity-stream.aspx?n=GovernorBeshear&amp;prId=2789) of Kentucky should appoint a successor to McConnell unless someone can prove he’s actually alive. The Democrats always put up with Republican tricks like this one. I'm sure McConnell would appreciate the utility of his death, and the Republican lack of shame. Anything for a buck.</source:markdown>
			<source:outline text="Obama should have &lt;a href=&quot;http://scripting.com/2022/06/24/141809.html?title=itShouldntBe63&quot;&gt;seated Garland&lt;/a&gt; if the Senate wouldn’t have  a vote to advise and consent. Assume they consent. In the same way, the &lt;a href=&quot;https://www.kentucky.gov/Pages/Activity-stream.aspx?n=GovernorBeshear&amp;prId=2789&quot;&gt;governor&lt;/a&gt; of Kentucky should appoint a successor to McConnell unless someone can prove he’s actually alive. The Democrats always put up with Republican tricks like this one. I'm sure McConnell would appreciate the utility of his death, and the Republican lack of shame. Anything for a buck." created="Tue, 01 Sep 2026 20:10:30 GMT" type="outline" image="https://imgs.scripting.com/2020/05/02/lbj.png" flInCalendar="true" permalink="http://scripting.com/2026/09/01.html#a201030"/>
			</item>
		<item>
			<description>Creative computer people, consider consolidating all the different OSes and programming languages. Give humans a fair fight in competition with the AI's who have no trouble deeply understanding every syntax human designers have come up with, where it totally disadvantages us, who have much more limited memory.</description>
			<pubDate>Tue, 01 Sep 2026 13:37:50 GMT</pubDate>
			<link>http://scripting.com/2026/09/01.html#a133750</link>
			<guid>http://scripting.com/2026/09/01.html#a133750</guid>
			<source:markdown>Creative computer people, consider consolidating all the different OSes and programming languages. Give humans a fair fight in competition with the AI's who have no trouble deeply understanding every syntax human designers have come up with, where it totally disadvantages us, who have much more limited memory.</source:markdown>
			<source:outline text="Creative computer people, consider consolidating all the different OSes and programming languages. Give humans a fair fight in competition with the AI's who have no trouble deeply understanding every syntax human designers have come up with, where it totally disadvantages us, who have much more limited memory." created="Tue, 01 Sep 2026 13:37:50 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/01.html#a133750"/>
			</item>
		<item>
			<description>If you View Source on a &lt;a href=&quot;http://scripting.com/2026/08/31.html#a155649&quot;&gt;fatpage&lt;/a&gt;, scroll to the bottom, you'll see the code. &lt;a href=&quot;http://scripting.com/fatpages/suites/slideShow.html&quot;&gt;Example&lt;/a&gt;. The idea is that the docs for the code are what you see in the browser. Maybe that's the way feeds should work too? Something to think about.</description>
			<pubDate>Tue, 01 Sep 2026 13:17:05 GMT</pubDate>
			<link>http://scripting.com/2026/09/01.html#a131705</link>
			<guid>http://scripting.com/2026/09/01.html#a131705</guid>
			<source:markdown>If you View Source on a [fatpage](http://scripting.com/2026/08/31.html#a155649), scroll to the bottom, you'll see the code. [Example](http://scripting.com/fatpages/suites/slideShow.html). The idea is that the docs for the code are what you see in the browser. Maybe that's the way feeds should work too? Something to think about.</source:markdown>
			<source:outline text="If you View Source on a &lt;a href=&quot;http://scripting.com/2026/08/31.html#a155649&quot;&gt;fatpage&lt;/a&gt;, scroll to the bottom, you'll see the code. &lt;a href=&quot;http://scripting.com/fatpages/suites/slideShow.html&quot;&gt;Example&lt;/a&gt;. The idea is that the docs for the code are what you see in the browser. Maybe that's the way feeds should work too? Something to think about." created="Tue, 01 Sep 2026 13:17:05 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/01.html#a131705"/>
			</item>
		<item>
			<description>&lt;img class=&quot;imgRightMargin&quot; src=&quot;https://imgs.scripting.com/2025/08/28/thinkDifferentBillboard.png&quot; border=&quot;0&quot; style=&quot;float: right; padding-left: 25px; padding-bottom: 10px; padding-top: 10px; padding-right: 15px;&quot;&gt;I begin the month of September for some reason, not feeling like working. And rather than succumb to the work ethos, I'm allowing myself to goof off with the same determination that I worked my ass of for so many years. I think the last time I felt like this was when I was a grad student in Madison. I had just fallen in love with a sweet, funny, cute and gorgeous undergrad. She was 19 and I was 22. We spent the last weeks of the fall semester goofing off, and as a result I had to stay in Madison over the holidays, to finish the work of the Compiler Design &lt;a href=&quot;https://pages.cs.wisc.edu/~cs701-1/&quot;&gt;course&lt;/a&gt;, which was the gate for grad students, the hardest course. If you got through it with a decent grade, you got the degree. It was fun too -- except I missed my sweetheart. This time I don't know what the root is, but it's a good feeling. If I want to goof off, I can, no one will judge me, probably very few people even notice. I still expect to finish Frontier, and swing back around to FeedLand and RSS.chat, they have some important work to do, together. Maybe the reason is the thing I liked about making software is the actual making of it, which I delegate more and more to Claude Code. How would a great painter feel if they invented a computer that could write their &quot;code&quot; much more quickly, would Picasso have stopped painting just because Claude Code could do Picasso paintings faster? Today, Claude still will, if given a chance, throw out all of my orders and develop code in a non-Dave fashion. And it still acts as if between the two of us it's the only programmer, surprised when I want to actually write something myself. Maybe that's just my imagination? Or maybe that's the next project for me. A project where I write the code, and Claude helps out when I can't find a bug, or where I need to know something about a feature in a platform I've not worked on.</description>
			<pubDate>Tue, 01 Sep 2026 13:05:57 GMT</pubDate>
			<link>http://scripting.com/2026/09/01.html#a130557</link>
			<guid>http://scripting.com/2026/09/01.html#a130557</guid>
			<source:markdown>![](https://imgs.scripting.com/2025/08/28/thinkDifferentBillboard.png)I begin the month of September for some reason, not feeling like working. And rather than succumb to the work ethos, I'm allowing myself to goof off with the same determination that I worked my ass of for so many years. I think the last time I felt like this was when I was a grad student in Madison. I had just fallen in love with a sweet, funny, cute and gorgeous undergrad. She was 19 and I was 22. We spent the last weeks of the fall semester goofing off, and as a result I had to stay in Madison over the holidays, to finish the work of the Compiler Design [course](https://pages.cs.wisc.edu/~cs701-1/), which was the gate for grad students, the hardest course. If you got through it with a decent grade, you got the degree. It was fun too -- except I missed my sweetheart. This time I don't know what the root is, but it's a good feeling. If I want to goof off, I can, no one will judge me, probably very few people even notice. I still expect to finish Frontier, and swing back around to FeedLand and RSS.chat, they have some important work to do, together. Maybe the reason is the thing I liked about making software is the actual making of it, which I delegate more and more to Claude Code. How would a great painter feel if they invented a computer that could write their &quot;code&quot; much more quickly, would Picasso have stopped painting just because Claude Code could do Picasso paintings faster? Today, Claude still will, if given a chance, throw out all of my orders and develop code in a non-Dave fashion. And it still acts as if between the two of us it's the only programmer, surprised when I want to actually write something myself. Maybe that's just my imagination? Or maybe that's the next project for me. A project where I write the code, and Claude helps out when I can't find a bug, or where I need to know something about a feature in a platform I've not worked on.</source:markdown>
			<source:outline text="I begin the month of September for some reason, not feeling like working. And rather than succumb to the work ethos, I'm allowing myself to goof off with the same determination that I worked my ass of for so many years. I think the last time I felt like this was when I was a grad student in Madison. I had just fallen in love with a sweet, funny, cute and gorgeous undergrad. She was 19 and I was 22. We spent the last weeks of the fall semester goofing off, and as a result I had to stay in Madison over the holidays, to finish the work of the Compiler Design &lt;a href=&quot;https://pages.cs.wisc.edu/~cs701-1/&quot;&gt;course&lt;/a&gt;, which was the gate for grad students, the hardest course. If you got through it with a decent grade, you got the degree. It was fun too -- except I missed my sweetheart. This time I don't know what the root is, but it's a good feeling. If I want to goof off, I can, no one will judge me, probably very few people even notice. I still expect to finish Frontier, and swing back around to FeedLand and RSS.chat, they have some important work to do, together. Maybe the reason is the thing I liked about making software is the actual making of it, which I delegate more and more to Claude Code. How would a great painter feel if they invented a computer that could write their &quot;code&quot; much more quickly, would Picasso have stopped painting just because Claude Code could do Picasso paintings faster? Today, Claude still will, if given a chance, throw out all of my orders and develop code in a non-Dave fashion. And it still acts as if between the two of us it's the only programmer, surprised when I want to actually write something myself. Maybe that's just my imagination? Or maybe that's the next project for me. A project where I write the code, and Claude helps out when I can't find a bug, or where I need to know something about a feature in a platform I've not worked on." created="Tue, 01 Sep 2026 13:05:57 GMT" type="outline" image="https://imgs.scripting.com/2025/08/28/thinkDifferentBillboard.png" flInCalendar="true" permalink="http://scripting.com/2026/09/01.html#a130557"/>
			</item>
		<item>
			<description>&lt;a href=&quot;https://github.com/scripting/Scripting-News/blob/master/blog/opml/2026/08.opml&quot;&gt;OPML archive&lt;/a&gt; for August 2026.</description>
			<pubDate>Tue, 01 Sep 2026 13:33:23 GMT</pubDate>
			<link>http://scripting.com/2026/09/01.html#a133323</link>
			<guid>http://scripting.com/2026/09/01.html#a133323</guid>
			<source:markdown>[OPML archive](https://github.com/scripting/Scripting-News/blob/master/blog/opml/2026/08.opml) for August 2026.</source:markdown>
			<source:outline text="&lt;a href=&quot;https://github.com/scripting/Scripting-News/blob/master/blog/opml/2026/08.opml&quot;&gt;OPML archive&lt;/a&gt; for August 2026." created="Tue, 01 Sep 2026 13:33:23 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/01.html#a133323"/>
			</item>
		<item>
			<title>Every writer everywhere</title>
			<description>&lt;p&gt;&lt;div class=&quot;divInlineImage&quot;&gt;&lt;center&gt;&lt;img class=&quot;imgInline&quot; src=&quot;https://imgs.scripting.com/2026/09/01/writerAlways.png&quot;&gt;&lt;/center&gt;Understands.&lt;/div&gt;&lt;/p&gt;&#10;</description>
			<pubDate>Tue, 01 Sep 2026 20:26:29 GMT</pubDate>
			<link>http://scripting.com/2026/09/01/202629.html?title=everyWriterEverywhere</link>
			<guid>http://scripting.com/2026/09/01/202629.html</guid>
			<source:markdown>![](https://imgs.scripting.com/2026/09/01/writerAlways.png)&#10;&#10;Understands.</source:markdown>
			<source:outline text="Every writer everywhere" created="Tue, 01 Sep 2026 20:26:29 GMT" type="outline" flInCalendar="true" permalink="http://scripting.com/2026/09/01/202629.html">
				<source:outline text="Understands." created="Tue, 01 Sep 2026 20:26:36 GMT" inlineImage="https://imgs.scripting.com/2026/09/01/writerAlways.png" flInCalendar="true" permalink="http://scripting.com/2026/09/01/202629.html#a202636"/>
				</source:outline>
			</item>
		</channel>
	</rss>
